Mitigating bias in machine learning for medicine

Several sources of bias can affect the performance of machine learning systems used in medicine and potentially impact clinical care. Here, we discuss solutions to mitigate bias across the different development steps of machine learning-based systems for medical applications. Vokinger et al. discuss...

Full description

Saved in:
Bibliographic Details
Published inCommunications medicine Vol. 1; no. 1; p. 25
Main Authors Vokinger, Kerstin N., Feuerriegel, Stefan, Kesselheim, Aaron S.
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 23.08.2021
Springer Nature B.V
Subjects
692/308
692/700
Algorithms
Artificial intelligence
Clinical medicine
Comment
Data collection
Machine learning
Medicine
Medicine & Public Health
Melanoma
Patients
Risk factors
Skin cancer
Software
United States > US
Online AccessGet full text
ISSN2730-664X
2730-664X
DOI10.1038/s43856-021-00028-w

Cover

More Information
Summary:Several sources of bias can affect the performance of machine learning systems used in medicine and potentially impact clinical care. Here, we discuss solutions to mitigate bias across the different development steps of machine learning-based systems for medical applications. Vokinger et al. discuss potential sources of bias in machine learning systems used in medicine. The authors propose solutions to mitigate bias across the different stages of model development, from data collection and preparation to model evaluation and application.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2730-664X
2730-664X
DOI:10.1038/s43856-021-00028-w